[WebAssembly] Constant fold wasm.dot (#149619)

Constant fold wasm.dot of constant vectors/splats.

Test case added in
`llvm/test/Transforms/InstSimplify/ConstProp/WebAssembly/dot.ll`

Related to #55933

Author: badumbatish

llvm/lib/Analysis/ConstantFolding.cpp

@@ -1659,6 +1659,7 @@ bool llvm::canConstantFoldCallTo(const CallBase *Call, const Function *F) {
   case Intrinsic::aarch64_sve_convert_from_svbool:
   case Intrinsic::wasm_alltrue:
   case Intrinsic::wasm_anytrue:
+  case Intrinsic::wasm_dot:
   // WebAssembly float semantics are always known
   case Intrinsic::wasm_trunc_signed:
   case Intrinsic::wasm_trunc_unsigned:
@@ -3989,6 +3990,30 @@ static Constant *ConstantFoldFixedVectorCall(
     }
     return ConstantVector::get(Result);
   }
+  case Intrinsic::wasm_dot: {
+    unsigned NumElements =
+        cast<FixedVectorType>(Operands[0]->getType())->getNumElements();
+
+    assert(NumElements == 8 && Result.size() == 4 &&
+           "wasm dot takes i16x8 and produces i32x4");
+    assert(Ty->isIntegerTy());
+    int32_t MulVector[8];
+
+    for (unsigned I = 0; I < NumElements; ++I) {
+      ConstantInt *Elt0 =
+          cast<ConstantInt>(Operands[0]->getAggregateElement(I));
+      ConstantInt *Elt1 =
+          cast<ConstantInt>(Operands[1]->getAggregateElement(I));
+
+      MulVector[I] = Elt0->getSExtValue() * Elt1->getSExtValue();
+    }
+    for (unsigned I = 0; I < Result.size(); I++) {
+      int32_t IAdd = MulVector[I * 2] + MulVector[I * 2 + 1];
+      Result[I] = ConstantInt::get(Ty, IAdd);
+    }
+
+    return ConstantVector::get(Result);
+  }
   default:
     break;
   }

llvm/test/Transforms/InstSimplify/ConstProp/WebAssembly/dot.ll

@@ -0,0 +1,56 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+
+; RUN: opt -passes=instsimplify -S < %s | FileCheck %s
+
+; Test that intrinsics wasm dot call are constant folded
+
+target triple = "wasm32-unknown-unknown"
+
+
+define <4 x i32> @dot_zero() {
+; CHECK-LABEL: define <4 x i32> @dot_zero() {
+; CHECK-NEXT:    ret <4 x i32> zeroinitializer
+;
+  %res = tail call <4 x i32> @llvm.wasm.dot(<8 x i16> zeroinitializer, <8 x i16> zeroinitializer)
+  ret <4 x i32> %res
+}
+
+; a               =   1    2    3    4    5    6    7    8
+; b               =   1    2    3    4    5    6    7    8
+; k1|k2 = a * b   =   1    4    9   16   25   36   49   64
+; k1 + k2         =   (1+4) |  (9 + 16) | (25 + 36)  | (49 + 64)
+; result          =    5    |   25    |   61    |   113
+define <4 x i32> @dot_nonzero() {
+; CHECK-LABEL: define <4 x i32> @dot_nonzero() {
+; CHECK-NEXT:    ret <4 x i32> <i32 5, i32 25, i32 61, i32 113>
+;
+  %res = tail call <4 x i32> @llvm.wasm.dot(<8 x i16> <i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8>, <8 x i16> <i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8>)
+  ret <4 x i32> %res
+}
+
+define <4 x i32> @dot_doubly_negative() {
+; CHECK-LABEL: define <4 x i32> @dot_doubly_negative() {
+; CHECK-NEXT:    ret <4 x i32> splat (i32 2)
+;
+  %res = tail call <4 x i32> @llvm.wasm.dot(<8 x i16> <i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1>, <8 x i16> <i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1>)
+  ret <4 x i32> %res
+}
+
+; Tests that i16 max signed values fit in i32
+define <4 x i32> @dot_follow_modulo_spec_1() {
+; CHECK-LABEL: define <4 x i32> @dot_follow_modulo_spec_1() {
+; CHECK-NEXT:    ret <4 x i32> <i32 2147352578, i32 0, i32 0, i32 0>
+;
+  %res = tail call <4 x i32> @llvm.wasm.dot(<8 x i16> <i16 32767, i16 32767, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>, <8 x i16> <i16 32767, i16 32767, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>)
+  ret <4 x i32> %res
+}
+
+; Tests that i16 min signed values fit in i32
+define <4 x i32> @dot_follow_modulo_spec_2() {
+; CHECK-LABEL: define <4 x i32> @dot_follow_modulo_spec_2() {
+; CHECK-NEXT:    ret <4 x i32> <i32 -2147483648, i32 0, i32 0, i32 0>
+;
+  %res = tail call <4 x i32> @llvm.wasm.dot(<8 x i16> <i16 -32768, i16 -32768, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>, <8 x i16> <i16 -32768, i16 -32768, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>)
+  ret <4 x i32> %res
+}
+